© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89217
    Prev
    Next
    INDEX
    Explanations

    references to educational techniques and psychological methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reamble
    -0.07
    arra
    -0.07
    antity
    -0.07
    aç
    -0.06
    loquent
    -0.06
    Ī¬
    -0.06
     بس
    -0.06
    voke
    -0.06
    esium
    -0.06
    íķĺìĭł
    -0.06
    POSITIVE LOGITS
     method
    0.08
    _appro
    0.07
     system
    0.07
    /System
    0.07
     Method
    0.07
     bran
    0.07
     approach
    0.07
     style
    0.07
    æĸ¹æ³ķ
    0.07
    à¹ģà¸ļà¸ļ
    0.07
    Activations Density 0.041%

    No Known Activations